Estimating Forest Volume and Biomass and Their Changes Using Random Forests and Remotely Sensed Data

被引:74
作者
Esteban, Jessica [1 ,2 ]
McRoberts, Ronald E. [3 ,4 ]
Fernandez-Landa, Alfredo [2 ]
Luis Tome, Jose [2 ]
Naesset, Erik [5 ]
机构
[1] Univ Politecn Madrid, Dept Topog & Geomat, E-28040 Madrid, Spain
[2] Agresta Soc Coop, Madrid 28012, Spain
[3] US Forest Serv, Northern Res Stn, St Paul, MN 55108 USA
[4] Univ Minnesota, Dept Forest Resources, St Paul, MN 55108 USA
[5] Norwegian Univ Life Sci, Fac Environm Sci & Nat Resource Management, POB 5003, NO-1432 As, Norway
关键词
bootstrapping; model-assisted; model-based; population parameters; MODEL-BASED INFERENCE; LANDSAT TIME-SERIES; ASSISTED ESTIMATION; AIRBORNE LIDAR; TREE-HEIGHT; ABOVEGROUND BIOMASS; HEDMARK COUNTY; SCANNING ANGLE; AUXILIARY DATA; SAMPLE SURVEY;
D O I
10.3390/rs11161944
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Despite the popularity of random forests (RF) as a prediction algorithm, methods for constructing confidence intervals for population means using this technique are still only sparsely reported. For two regional study areas (Spain and Norway) RF was used to predict forest volume or aboveground biomass using remotely sensed auxiliary data obtained from multiple sensors. Additionally, the changes per unit area of these forest attributes were estimated using indirect and direct methods. Multiple inferential frameworks have attracted increased recent attention for estimating the variances required for confidence intervals. For this study, three different statistical frameworks, design-based expansion, model-assisted and model-based estimators, were used for estimating population parameters and their variances. Pairs and wild bootstrapping approaches at different levels were compared for estimating the variances of the model-based estimates of the population means, as well as for mapping the uncertainty of the change predictions. The RF models accurately represented the relationship between the response and remotely sensed predictor variables, resulting in increased precision for estimates of the population means relative to design-based expansion estimates. Standard errors based on pairs bootstrapping within or internal to RF were considerably larger than standard errors based on both pairs and wild external bootstrapping of the entire RF algorithm. Pairs and wild external bootstrapping produced similar standard errors, but wild bootstrapping better mimicked the original structure of the sample data and better preserved the ranges of the predictor variables.
引用
收藏
页数:21
相关论文
共 80 条
[1]   Characterizing stand-level forest canopy cover and height using Landsat time series, samples of airborne LiDAR, and the Random Forest algorithm [J].
Ahmed, Oumer S. ;
Franklin, Steven E. ;
Wulder, Michael A. ;
White, Joanne C. .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2015, 101 :89-101
[2]  
Alberdi I., 2017, Pesquisa Florestal Brasileira, V37, P361, DOI 10.4336/2017.pfb.37.91.1337
[3]   National Forest,Inventory and forest observational studies in Spain: Applications to forest modeling [J].
Alvarez-Gonzalez, J. G. ;
Canellas, I. ;
Alberdi, I. ;
Gadow, K. V. ;
Ruiz-Gonzalez, A. D. .
FOREST ECOLOGY AND MANAGEMENT, 2014, 316 :54-64
[4]   Monitoring selective logging in western Amazonia with repeat lidar flights [J].
Andersen, Hans-Erik ;
Reutebuch, Stephen E. ;
McGaughey, Robert J. ;
d'Oliveira, Marcus V. N. ;
Keller, Michael .
REMOTE SENSING OF ENVIRONMENT, 2014, 151 :157-165
[5]  
[Anonymous], 2005, STAT TRANSITION
[6]   Testing the quality of forest variable estimation using dense image matching: a comparison with airborne laser scanning in a Mediterranean pine forest [J].
Antonio Navarro, Jose ;
Fernandez-Landa, Alfredo ;
Luis Tome, Jose ;
Luz Guillen-Climent, Maria ;
Carlos Ojeda, Juan .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2018, 39 (14) :4744-4760
[7]   Forest Monitoring Using Landsat Time Series Data: A Review [J].
Banskota, Asim ;
Kayastha, Nilam ;
Falkowski, Michael J. ;
Wulder, Michael A. ;
Froese, Robert E. ;
White, Joanne C. .
CANADIAN JOURNAL OF REMOTE SENSING, 2014, 40 (05) :362-384
[8]   A questionnaire-based review of the operational use of remotely sensed data by national forest inventories [J].
Barrett, Frank ;
McRoberts, Ronald E. ;
Tomppo, Erkki ;
Cienciala, Emil ;
Waser, Lars T. .
REMOTE SENSING OF ENVIRONMENT, 2016, 174 :279-289
[9]   Random forest in remote sensing: A review of applications and future directions [J].
Belgiu, Mariana ;
Dragut, Lucian .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2016, 114 :24-31
[10]   Model-Assisted Survey Estimation with Modern Prediction Techniques [J].
Breidt, F. Jay ;
Opsomer, Jean D. .
STATISTICAL SCIENCE, 2017, 32 (02) :190-205